{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T10:03:15Z","timestamp":1784282595905,"version":"3.55.0"},"reference-count":80,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T00:00:00Z","timestamp":1784246400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"CIASUR","award":["MSTCTU0010253TC"],"award-info":[{"award-number":["MSTCTU0010253TC"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Predictive maintenance (PdM) is central to Industry 5.0 strategies for reducing unplanned downtime in rotating machinery. This work proposes and evaluates, as a proof of concept on a controlled single-machine testbed, a multimodal TinyML edge architecture for PdM designed to remain compatible across the application plane\u2019s evolution toward sixth-generation (6G) networks. Three complementary modalities run local inference on commercial off-the-shelf smart sensor nodes\u2014vibration, acoustic, and thermography\u2014with an embedded gateway bridging per-modality decisions to a serverless cloud back-end. Using real vibration data from a controlled static-unbalance protocol, five anomaly-detection model variants, operating on ten frequency-independent time-domain features extracted from 6 s windows, are benchmarked on the actual Cortex-M4F target; the INT8-quantized fully connected autoencoder, scored by per-window reconstruction error, reaches F1 = 0.9807 with 254 \u00b5s inference latency and a 6056 B Flash footprint, well within the microcontroller budget. In a second acquisition session with the remounted sensor, the frozen model retains perfect fault recall, and a short per-installation healthy-baseline recalibration restores F1 = 0.975 without any weight retraining. The acoustic modality is classified in-sensor on log-Mel filterbank energies by the Syntiant NDP120 neural coprocessor, and the thermographic modality by a lightweight binary CNN on 96 \u00d7 96 px frames. A preliminary intra-session late-fusion analysis suggests that a logistic-regression meta-learner over the three modality confidence scores can improve on single-modality baselines when no single modality already saturates, motivating multimodal sensing primarily for robustness and redundancy. An end-to-end latency experiment shows that the cloud-uplink leg dominates the budget (79\u201388%), establishing edge-first inference as a necessary condition for 6G URLLC gains to be observable at the application level. All experiments are conducted over Wi-Fi and MQTT with no 5G or 6G radio, so 6G compatibility is presented as a forward-looking roadmap rather than a tested capability.<\/jats:p>","DOI":"10.3390\/s26144536","type":"journal-article","created":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T09:00:52Z","timestamp":1784278852000},"page":"4536","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Multimodal TinyML-Based Predictive Maintenance Architecture for Industrial IoT in the 6G Era"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3734-2968","authenticated-orcid":false,"given":"Carlos Exequiel","family":"Garay","sequence":"first","affiliation":[{"name":"CIASUR (Centro de Investigaci\u00f3n de Atm\u00f3sfera Superior y Radiopropagaci\u00f3n), Facultad Regional Tucum\u00e1n (FRT), Universidad Tecnol\u00f3gica Nacional (UTN), Rivadavia 1050, San Miguel de Tucum\u00e1n 4000, Argentina"},{"name":"Laboratorio de Telecomunicaciones (LTC), Departamento de Electricidad, Electr\u00f3nica y Computaci\u00f3n, Facultad de Ciencias Exactas y Tecnolog\u00eda (FACET), Universidad Nacional de Tucum\u00e1n (UNT), San Miguel de Tucum\u00e1n 4000, Argentina"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1579-0776","authenticated-orcid":false,"given":"Fernando Alberto","family":"Miranda Bonomi","sequence":"additional","affiliation":[{"name":"Laboratorio de Telecomunicaciones (LTC), Departamento de Electricidad, Electr\u00f3nica y Computaci\u00f3n, Facultad de Ciencias Exactas y Tecnolog\u00eda (FACET), Universidad Nacional de Tucum\u00e1n (UNT), San Miguel de Tucum\u00e1n 4000, Argentina"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gonzalo Nicol\u00e1s","family":"Mansilla","sequence":"additional","affiliation":[{"name":"CIASUR (Centro de Investigaci\u00f3n de Atm\u00f3sfera Superior y Radiopropagaci\u00f3n), Facultad Regional Tucum\u00e1n (FRT), Universidad Tecnol\u00f3gica Nacional (UTN), Rivadavia 1050, San Miguel de Tucum\u00e1n 4000, Argentina"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0073-6371","authenticated-orcid":false,"given":"Mariano","family":"Fagre","sequence":"additional","affiliation":[{"name":"Laboratorio de Telecomunicaciones (LTC), Departamento de Electricidad, Electr\u00f3nica y Computaci\u00f3n, Facultad de Ciencias Exactas y Tecnolog\u00eda (FACET), Universidad Nacional de Tucum\u00e1n (UNT), San Miguel de Tucum\u00e1n 4000, Argentina"},{"name":"Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas (CONICET), San Miguel de Tucum\u00e1n 4000, Argentina"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sergio Gustavo","family":"Guzm\u00e1n","sequence":"additional","affiliation":[{"name":"Laboratorio \u00c1rea IV\u2014Termolog\u00eda, Departamento de Mec\u00e1nica, Facultad Regional Tucum\u00e1n (FRT), Universidad Tecnol\u00f3gica Nacional (UTN), Rivadavia 1050, San Miguel de Tucum\u00e1n 4000, Argentina"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pablo Alberto","family":"Ritorto","sequence":"additional","affiliation":[{"name":"Laboratorio \u00c1rea IV\u2014Termolog\u00eda, Departamento de Mec\u00e1nica, Facultad Regional Tucum\u00e1n (FRT), Universidad Tecnol\u00f3gica Nacional (UTN), Rivadavia 1050, San Miguel de Tucum\u00e1n 4000, Argentina"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Franco Ismael","family":"Perez","sequence":"additional","affiliation":[{"name":"Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas (CONICET), San Miguel de Tucum\u00e1n 4000, Argentina"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marcos","family":"Katz","sequence":"additional","affiliation":[{"name":"Centre for Wireless Communications, University of Oulu, 90014 Oulu, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,17]]},"reference":[{"key":"ref_1","unstructured":"Zhu, T., Ran, Y., Zhou, X., and Wen, Y. (2019). A Survey of Predictive Maintenance: Systems, Purposes and Approaches. arXiv."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"67","DOI":"10.11113\/jurnalteknologi.v85.19416","article-title":"Anomaly detection in the temperature of an AC motor using embedded machine learning","volume":"85","author":"Ismail","year":"2023","journal-title":"J. Teknol."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Aung, K.H.H., Kok, C.L., Koh, Y.Y., and Teo, T.H. (2024). An embedded machine learning fault detection system for electric fan drive. Electronics, 13.","DOI":"10.3390\/electronics13030493"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Suawa, P., Meisel, T., Jongmanns, M., Huebner, M., and Reichenbach, M. (2022). Modeling and fault detection of brushless direct current motor by deep learning sensor data fusion. Sensors, 22.","DOI":"10.3390\/s22093516"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Givnan, S., Chalmers, C., Fergus, P., Ortega-Martorell, S., and Whalley, T. (2022). Anomaly detection using autoencoder reconstruction upon industrial motors. Sensors, 22.","DOI":"10.3390\/s22093166"},{"key":"ref_6","first-page":"184861","article-title":"A holistic review of the TinyML stack for predictive maintenance","volume":"12","author":"Njor","year":"2024","journal-title":"IEEE Access"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Reis, M.J.C.S. (2025). Lightweight signal processing and edge AI for real-time anomaly detection in IoT sensor networks. Sensors, 25.","DOI":"10.3390\/s25216629"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Hamdan, S., Ayyash, M., and Almajali, S. (2020). Edge-computing architectures for Internet of Things applications: A survey. Sensors, 20.","DOI":"10.3390\/s20226441"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1145\/3586991","article-title":"Machine learning sensors","volume":"66","author":"Warden","year":"2023","journal-title":"Commun. ACM"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Guo, S., and Zhou, Q. (2022). Machine Learning on Commodity Tiny Devices: Theory and Practice, CRC Press.","DOI":"10.1201\/9781003340225"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"24910","DOI":"10.1109\/ACCESS.2018.2890302","article-title":"Spectrum gap analysis with practical solutions for future mobile data traffic growth in Malaysia","volume":"7","author":"Shayea","year":"2019","journal-title":"IEEE Access"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1109\/MNET.001.1900287","article-title":"A vision of 6G wireless systems: Applications, trends, technologies, and open research problems","volume":"34","author":"Saad","year":"2020","journal-title":"IEEE Netw."},{"key":"ref_13","unstructured":"ITU-R (2023). Recommendation ITU-R M.2160-0: Framework and Overall Objectives of the Future Development of IMT for 2030 and Beyond, ITU."},{"key":"ref_14","unstructured":"3GPP (2026, May 01). Release 20 Description; 5G-Advanced and 6G Studies. Available online: https:\/\/www.3gpp.org\/specifications-technologies\/releases\/release-20."},{"key":"ref_15","unstructured":"Situnayake, D., and Plunkett, J. (2023). AI at the Edge: Solving Real-World Problems with Embedded Machine Learning, O\u2019Reilly Media."},{"key":"ref_16","unstructured":"Warden, P., and Situnayake, D. (2019). TinyML: Machine Learning with TensorFlow Lite on Arduino and Ultra-Low-Power Microcontrollers, O\u2019Reilly Media."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"29015","DOI":"10.1007\/s11042-023-16740-9","article-title":"TinyML: Tools, applications, challenges, and future research directions","volume":"83","author":"Kallimani","year":"2024","journal-title":"Multimed. Tools Appl."},{"key":"ref_18","unstructured":"(2026, April 01). TensorFlow Lite for Microcontrollers. Available online: https:\/\/www.tensorflow.org\/lite\/microcontrollers."},{"key":"ref_19","unstructured":"(2026, April 01). Edge Impulse. Available online: https:\/\/edgeimpulse.com\/."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1007\/s43926-025-00142-4","article-title":"IoT device for detecting abnormal vibrations in motors using TinyML","volume":"5","author":"Arciniegas","year":"2025","journal-title":"Discov. Internet Things"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Tanuska, P., Spendla, L., Kebisek, M., Duris, R., and Stremy, M. (2021). Smart anomaly detection and prediction for assembly process maintenance in compliance with Industry 4.0. Sensors, 21.","DOI":"10.3390\/s21072376"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Li, Z., Fei, F., and Zhang, G. (2022). Edge-to-cloud IIoT for condition monitoring in manufacturing systems with ubiquitous smart sensors. Sensors, 22.","DOI":"10.3390\/s22155901"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Kolok, P., Hodo\u0148, M., \u0160ev\u010d\u00edk, P., Hotz, L., and Remy, N. (2025). Low-cost IoT-based predictive maintenance using vibration and acoustic signals on MEMS sensors. Sensors, 25.","DOI":"10.3390\/s25216610"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Alharthi, S., Rashid, M., and Aljabri, M. (2026). TinyML in Industrial IoT: A Systematic Review of Applications, System Components, and Methodologies. Sensors, 26.","DOI":"10.3390\/s26082550"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Elmoutaoukkil, A., Chriss, M., Khatib, A., and Mouchtachi, A. (2024). Industry 4.0 Efficiency: Predictive Maintenance with TinyML and an Incremental Model. Smart Applications and Data Analysis (SADASC 2024), Springer. Communications in Computer and Information Science.","DOI":"10.1007\/978-3-031-77040-1_19"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Antonini, M., Pincheira, M., Vecchio, M., and Antonelli, F. (2023). An Adaptable and Unsupervised TinyML Anomaly Detection System for Extreme Industrial Environments. Sensors, 23.","DOI":"10.3390\/s23042344"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"19","DOI":"10.5755\/j01.eie.23.6.19690","article-title":"Two stage data fusion of acoustic, electric and vibration signals for diagnosing faults in induction motors","volume":"23","author":"Stief","year":"2017","journal-title":"Elektron. Elektrotech."},{"key":"ref_28","first-page":"3507848","article-title":"A Systematic Review of Multi-Sensor Information Fusion for Equipment Fault Diagnosis","volume":"74","author":"Lin","year":"2025","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Jiang, D., and Wang, Z. (2023). Research on mechanical equipment fault diagnosis method based on deep learning and information fusion. Sensors, 23.","DOI":"10.3390\/s23156999"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"105872","DOI":"10.1016\/j.engappai.2023.105872","article-title":"Multi-Input CNN Based Vibro-Acoustic Fusion for Accurate Fault Diagnosis of Induction Motor","volume":"120","author":"Choudhary","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"2113","DOI":"10.1080\/10589759.2024.2375567","article-title":"Smart Systems for Real-Time Bearing Faults Diagnosis by Using Vibro-Acoustics Sensor Fusion with Bayesian Optimised 1-D CNNs","volume":"40","author":"Mamun","year":"2025","journal-title":"Nondestruct. Test. Eval."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"110301","DOI":"10.1016\/j.apacoust.2024.110301","article-title":"Multimodal Fusion Fault Diagnosis Method Under Noise Interference","volume":"228","author":"Qiu","year":"2025","journal-title":"Appl. Acoust."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"20903","DOI":"10.1007\/s11071-024-10157-1","article-title":"A Performance-Interpretable Intelligent Fusion of Sound and Vibration Signals for Bearing Fault Diagnosis via Dynamic CAME","volume":"112","author":"Keshun","year":"2024","journal-title":"Nonlinear Dyn."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Xu, Z., Chen, X., Li, Y., and Xu, J. (2024). Hybrid Multimodal Feature Fusion with Multi-Sensor for Bearing Fault Diagnosis. Sensors, 24.","DOI":"10.3390\/s24061792"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Gu, X., Tian, Y., Li, C., Wei, Y., and Li, D. (2024). Improved SE-ResNet Acoustic\u2013Vibration Fusion for Rolling Bearing Composite Fault Diagnosis. Appl. Sci., 14.","DOI":"10.3390\/app14052182"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1016\/j.infrared.2015.09.004","article-title":"Thermal image based fault diagnosis for rotating machinery","volume":"73","author":"Janssens","year":"2015","journal-title":"Infrared Phys. Technol."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1016\/j.measurement.2016.07.008","article-title":"Diagnostics of stator faults of the single-phase induction motor using thermal images, MoASoS and selected classifiers","volume":"93","author":"Glowacz","year":"2016","journal-title":"Measurement"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/j.infrared.2013.03.006","article-title":"Infrared Thermography for Condition Monitoring\u2014A Review","volume":"60","author":"Bagavathiappan","year":"2013","journal-title":"Infrared Phys. Technol."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Wang, R., Zhan, X., Bai, H., Dong, E., Cheng, Z., and Jia, X. (2022). A Review of Fault Diagnosis Methods for Rotating Machinery Using Infrared Thermography. Micromachines, 13.","DOI":"10.3390\/mi13101644"},{"key":"ref_40","unstructured":"3GPP (2024). Study on AI\/ML for NR Air Interface (Release 18), 3GPP. TR 38.843."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"104040","DOI":"10.1016\/j.jnca.2024.104040","article-title":"On Challenges of Sixth-Generation (6G) Wireless Networks: A Comprehensive Survey of Requirements, Applications, and Security Issues","volume":"233","author":"Akbar","year":"2025","journal-title":"J. Netw. Comput. Appl."},{"key":"ref_42","unstructured":"3GPP (2017). 5G System Architecture, 3GPP. TS 23.501 V15.0.0."},{"key":"ref_43","unstructured":"3GPP (2018). 5G LAN Support, 3GPP. TR 22.821 V16.1.0."},{"key":"ref_44","unstructured":"3GPP (2024). Service Requirements for Cyber-Physical Control in Vertical Domains, 3GPP. TS 22.104 V19.2.0."},{"key":"ref_45","unstructured":"3GPP (2017). Service Requirements for the 5G System, 3GPP. TS 22.261 V15.0.0."},{"key":"ref_46","unstructured":"3GPP (2024). Study on Integrated Sensing and Communication (Release 19), 3GPP. TR 22.837."},{"key":"ref_47","unstructured":"3GPP (2024). Service Requirements for Integrated Sensing and Communication, 3GPP. TS 22.137."},{"key":"ref_48","unstructured":"(2026, April 01). Amazon Web Services IoT Core. Available online: https:\/\/aws.amazon.com\/iot-core\/."},{"key":"ref_49","unstructured":"(2026, April 01). Building Data Lakes on AWS. Available online: https:\/\/docs.aws.amazon.com\/whitepapers\/latest\/building-data-lakes\/amazon-s3-data-lake-storage-platform.html."},{"key":"ref_50","unstructured":"(2026, April 01). Real-Time Inference with Amazon SageMaker. Available online: https:\/\/docs.aws.amazon.com\/sagemaker\/latest\/dg\/realtime-single-model.html."},{"key":"ref_51","unstructured":"(2026, April 01). AWS Lambda Quotas. Available online: https:\/\/docs.aws.amazon.com\/lambda\/latest\/dg\/gettingstarted-limits.html."},{"key":"ref_52","unstructured":"(2007). Rolling Bearings\u2014Dynamic Load Ratings and Rating Life (Standard No. ISO 281:2007)."},{"key":"ref_53","unstructured":"Nectoux, P., Gouriveau, R., Medjaher, K., Ramasso, E., Chebel-Morello, B., Zerhouni, N., and Varnier, C. (2012, January 18\u201321). PRONOSTIA: An Experimental Platform for Bearings Accelerated Degradation Tests. Proceedings of the IEEE International Conference on Prognostics and Health Management (PHM\u201912), Denver, CO, USA."},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Mohanty, A.R. (2014). Machinery Condition Monitoring: Principles and Practices, CRC Press.","DOI":"10.1201\/9781351228626"},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Randall, R.B. (2011). Vibration-Based Condition Monitoring: Industrial, Aerospace and Automotive Applications, Wiley.","DOI":"10.1002\/9780470977668"},{"key":"ref_56","unstructured":"Taylor, J.I. (1994). The Vibration Analysis Handbook, Vibration Consultants."},{"key":"ref_57","unstructured":"Perera, P., Oza, P., and Patel, V.M. (2021). One-class classification: A survey. arXiv."},{"key":"ref_58","doi-asserted-by":"crossref","unstructured":"Mehrotra, K.G., Mohan, C.K., and Huang, H. (2017). Anomaly Detection: Principles and Algorithms, Springer.","DOI":"10.1007\/978-3-319-67526-8"},{"key":"ref_59","doi-asserted-by":"crossref","first-page":"270","DOI":"10.30811\/jpl.v23i3.6653","article-title":"Machine fault detection through sound analysis using MFCC and machine learning","volume":"23","author":"Chang","year":"2025","journal-title":"J. Polimesin"},{"key":"ref_60","doi-asserted-by":"crossref","unstructured":"Akbal\u0131k, F., Y\u0131ld\u0131z, A., Ertu\u011frul, \u00d6.F., and Zan, H. (2024). Engine fault detection by sound analysis and machine learning. Appl. Sci., 14.","DOI":"10.3390\/app14156532"},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"642","DOI":"10.1109\/TSMCC.2013.2257752","article-title":"Review of automatic fault diagnosis systems using audio and vibration signals","volume":"44","author":"Henriquez","year":"2014","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"ref_62","unstructured":"(2026, April 01). Arduino Nicla Voice User Manual. Available online: https:\/\/docs.arduino.cc\/tutorials\/nicla-voice\/user-manual\/."},{"key":"ref_63","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1016\/S0888-3270(03)00012-8","article-title":"Unsupervised noise cancellation for vibration signals: Part I\u2014Evaluation of adaptive algorithms","volume":"18","author":"Antoni","year":"2004","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_64","doi-asserted-by":"crossref","unstructured":"Alvarado-Hernandez, A.I., Zamudio-Ramirez, I., Jaen-Cuellar, A.Y., Osornio-Rios, R.A., Donderis-Quiles, V., and Antonino-Daviu, J.A. (2022). Infrared thermography smart sensor for the condition monitoring of gearbox and bearings faults in induction motors. Sensors, 22.","DOI":"10.3390\/s22166075"},{"key":"ref_65","doi-asserted-by":"crossref","unstructured":"Prattic\u00f2, D., Lagan\u00e0, F., Versaci, M., Frankovi\u0107, D., Jakopli\u0107, A., and La Foresta, F. (2025). Efficient Attentive U-Net for Fault Diagnosis and Predictive Maintenance of Photovoltaic Panels Through Infrared Thermography. Energies, 18.","DOI":"10.3390\/en18246472"},{"key":"ref_66","unstructured":"ITU-R (2017). Report ITU-R M.2410-0. Minimum Requirements Related to Technical Performance for IMT-2020 Radio Interface(s), ITU-R."},{"key":"ref_67","unstructured":"3GPP (2026). Study on 6G Scenarios and Requirements, 3GPP. work in progress."},{"key":"ref_68","unstructured":"3GPP (2025). Study on 6G Use Cases and Service Requirements (Stage 1), 3GPP. TR 22.870."},{"key":"ref_69","unstructured":"Nordic Semiconductor (2021). nRF52832 Product Specification, v1.8, Nordic Semiconductor ASA."},{"key":"ref_70","unstructured":"Bosch Sensortec (2021). BHI260AP: Self-Learning AI Smart Sensor with Integrated IMU, Bosch Sensortec GmbH. Datasheet BST-BHI260AP-DS000."},{"key":"ref_71","unstructured":"STMicroelectronics (2022). STM32H742xI\/G and STM32H743xI\/G Datasheet, DS12110, STMicroelectronics."},{"key":"ref_72","unstructured":"Teledyne FLIR (2023). FLIR Lepton Engineering Datasheet, Teledyne FLIR LLC. Document 500-0659-00-09."},{"key":"ref_73","unstructured":"Cypress Semiconductor (an Infineon Technologies company) (2020). CYW4343W Single-Chip 802.11 b\/g\/n MAC\/Baseband\/Radio with Integrated Bluetooth, Infineon Technologies AG. Datasheet 002-14797."},{"key":"ref_74","doi-asserted-by":"crossref","unstructured":"Bolat, Y., Murray, I., Ren, Y., and Ferdosian, N. (2025). Decentralized Distributed Sequential Neural Networks Inference on Low-Power Microcontrollers in Wireless Sensor Networks: A Predictive Maintenance Case Study. Sensors, 25.","DOI":"10.3390\/s25154595"},{"key":"ref_75","doi-asserted-by":"crossref","unstructured":"Liu, X., Dong, X., Jia, N., and Zhao, W. (2024). Federated learning-oriented edge computing framework for the IIoT. Sensors, 24.","DOI":"10.3390\/s24134182"},{"key":"ref_76","unstructured":"3GPP (2018). Study on the Support of 256-bit Algorithms for 5G, 3GPP. TR 33.841 V16.0.0."},{"key":"ref_77","unstructured":"3GPP (2018). 5G Security Architecture and Procedures, 3GPP. TS 33.501 V15.0.0."},{"key":"ref_78","unstructured":"NIST (2024). Module-Lattice-Based Key-Encapsulation and Signature Standards (ML-KEM, ML-DSA), NIST. FIPS 203\/FIPS 204."},{"key":"ref_79","unstructured":"3GPP (2023). Study on Ambient IoT Use Cases, 3GPP. TR 22.840."},{"key":"ref_80","unstructured":"3GPP (2023). Study on Ambient IoT in RAN, 3GPP. TR 38.848."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/14\/4536\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T09:08:11Z","timestamp":1784279291000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/14\/4536"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,17]]},"references-count":80,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["s26144536"],"URL":"https:\/\/doi.org\/10.3390\/s26144536","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,17]]}}}